"""
Binary serialization

NPY format
==========

A simple format for saving numpy arrays to disk with the full
information about them.

The ``.npy`` format is the standard binary file format in NumPy for
persisting a *single* arbitrary NumPy array on disk. The format stores all
of the shape and dtype information necessary to reconstruct the array
correctly even on another machine with a different architecture.
The format is designed to be as simple as possible while achieving
its limited goals.

The ``.npz`` format is the standard format for persisting *multiple* NumPy
arrays on disk. A ``.npz`` file is a zip file containing multiple ``.npy``
files, one for each array.

Capabilities
------------

- Can represent all NumPy arrays including nested record arrays and
  object arrays.

- Represents the data in its native binary form.

- Supports Fortran-contiguous arrays directly.

- Stores all of the necessary information to reconstruct the array
  including shape and dtype on a machine of a different
  architecture.  Both little-endian and big-endian arrays are
  supported, and a file with little-endian numbers will yield
  a little-endian array on any machine reading the file. The
  types are described in terms of their actual sizes. For example,
  if a machine with a 64-bit C "long int" writes out an array with
  "long ints", a reading machine with 32-bit C "long ints" will yield
  an array with 64-bit integers.

- Is straightforward to reverse engineer. Datasets often live longer than
  the programs that created them. A competent developer should be
  able to create a solution in their preferred programming language to
  read most ``.npy`` files that he has been given without much
  documentation.

- Allows memory-mapping of the data. See `open_memmep`.

- Can be read from a filelike stream object instead of an actual file.

- Stores object arrays, i.e. arrays containing elements that are arbitrary
  Python objects. Files with object arrays are not to be mmapable, but
  can be read and written to disk.

Limitations
-----------

- Arbitrary subclasses of numpy.ndarray are not completely preserved.
  Subclasses will be accepted for writing, but only the array data will
  be written out. A regular numpy.ndarray object will be created
  upon reading the file.

.. warning::

  Due to limitations in the interpretation of structured dtypes, dtypes
  with fields with empty names will have the names replaced by 'f0', 'f1',
  etc. Such arrays will not round-trip through the format entirely
  accurately. The data is intact; only the field names will differ. We are
  working on a fix for this. This fix will not require a change in the
  file format. The arrays with such structures can still be saved and
  restored, and the correct dtype may be restored by using the
  ``loadedarray.view(correct_dtype)`` method.

File extensions
---------------

We recommend using the ``.npy`` and ``.npz`` extensions for files saved
in this format. This is by no means a requirement; applications may wish
to use these file formats but use an extension specific to the
application. In the absence of an obvious alternative, however,
we suggest using ``.npy`` and ``.npz``.

Version numbering
-----------------

The version numbering of these formats is independent of NumPy version
numbering. If the format is upgraded, the code in `numpy.io` will still
be able to read and write Version 1.0 files.

Format Version 1.0
------------------

The first 6 bytes are a magic string: exactly ``\\x93NUMPY``.

The next 1 byte is an unsigned byte: the major version number of the file
format, e.g. ``\\x01``.

The next 1 byte is an unsigned byte: the minor version number of the file
format, e.g. ``\\x00``. Note: the version of the file format is not tied
to the version of the numpy package.

The next 2 bytes form a little-endian unsigned short int: the length of
the header data HEADER_LEN.

The next HEADER_LEN bytes form the header data describing the array's
format. It is an ASCII string which contains a Python literal expression
of a dictionary. It is terminated by a newline (``\\n``) and padded with
spaces (``\\x20``) to make the total of
``len(magic string) + 2 + len(length) + HEADER_LEN`` be evenly divisible
by 64 for alignment purposes.

The dictionary contains three keys:

    "descr" : dtype.descr
      An object that can be passed as an argument to the `numpy.dtype`
      constructor to create the array's dtype.
    "fortran_order" : bool
      Whether the array data is Fortran-contiguous or not. Since
      Fortran-contiguous arrays are a common form of non-C-contiguity,
      we allow them to be written directly to disk for efficiency.
    "shape" : tuple of int
      The shape of the array.

For repeatability and readability, the dictionary keys are sorted in
alphabetic order. This is for convenience only. A writer SHOULD implement
this if possible. A reader MUST NOT depend on this.

Following the header comes the array data. If the dtype contains Python
objects (i.e. ``dtype.hasobject is True``), then the data is a Python
pickle of the array. Otherwise the data is the contiguous (either C-
or Fortran-, depending on ``fortran_order``) bytes of the array.
Consumers can figure out the number of bytes by multiplying the number
of elements given by the shape (noting that ``shape=()`` means there is
1 element) by ``dtype.itemsize``.

Format Version 2.0
------------------

The version 1.0 format only allowed the array header to have a total size of
65535 bytes.  This can be exceeded by structured arrays with a large number of
columns.  The version 2.0 format extends the header size to 4 GiB.
`numpy.save` will automatically save in 2.0 format if the data requires it,
else it will always use the more compatible 1.0 format.

The description of the fourth element of the header therefore has become:
"The next 4 bytes form a little-endian unsigned int: the length of the header
data HEADER_LEN."

Format Version 3.0
------------------

This version replaces the ASCII string (which in practice was latin1) with
a utf8-encoded string, so supports structured types with any unicode field
names.

Notes
-----
The ``.npy`` format, including motivation for creating it and a comparison of
alternatives, is described in the `"npy-format" NEP
<https://www.numpy.org/neps/nep-0001-npy-format.html>`_, however details have
evolved with time and this document is more current.

"""
import numpy
import io
import warnings
from numpy.lib.utils import safe_eval
from numpy.compat import (
    isfileobj, os_fspath, pickle
    )


__all__ = []


MAGIC_PREFIX = b'\x93NUMPY'
MAGIC_LEN = len(MAGIC_PREFIX) + 2
ARRAY_ALIGN = 64 # plausible values are powers of 2 between 16 and 4096
BUFFER_SIZE = 2**18  # size of buffer for reading npz files in bytes

# difference between version 1.0 and 2.0 is a 4 byte (I) header length
# instead of 2 bytes (H) allowing storage of large structured arrays
_header_size_info = {
    (1, 0): ('<H', 'latin1'),
    (2, 0): ('<I', 'latin1'),
    (3, 0): ('<I', 'utf8'),
}


def _check_version(version):
    if version not in [(1, 0), (2, 0), (3, 0), None]:
        msg = "we only support format version (1,0), (2,0), and (3,0), not %s"
        raise ValueError(msg % (version,))

def magic(major, minor):
    """ Return the magic string for the given file format version.

    Parameters
    ----------
    major : int in [0, 255]
    minor : int in [0, 255]

    Returns
    -------
    magic : str

    Raises
    ------
    ValueError if the version cannot be formatted.
    """
    if major < 0 or major > 255:
        raise ValueError("major version must be 0 <= major < 256")
    if minor < 0 or minor > 255:
        raise ValueError("minor version must be 0 <= minor < 256")
    return MAGIC_PREFIX + bytes([major, minor])

def read_magic(fp):
    """ Read the magic string to get the version of the file format.

    Parameters
    ----------
    fp : filelike object

    Returns
    -------
    major : int
    minor : int
    """
    magic_str = _read_bytes(fp, MAGIC_LEN, "magic string")
    if magic_str[:-2] != MAGIC_PREFIX:
        msg = "the magic string is not correct; expected %r, got %r"
        raise ValueError(msg % (MAGIC_PREFIX, magic_str[:-2]))
    major, minor = magic_str[-2:]
    return major, minor

def _has_metadata(dt):
    if dt.metadata is not None:
        return True
    elif dt.names is not None:
        return any(_has_metadata(dt[k]) for k in dt.names)
    elif dt.subdtype is not None:
        return _has_metadata(dt.base)
    else:
        return False

def dtype_to_descr(dtype):
    """
    Get a serializable descriptor from the dtype.

    The .descr attribute of a dtype object cannot be round-tripped through
    the dtype() constructor. Simple types, like dtype('float32'), have
    a descr which looks like a record array with one field with '' as
    a name. The dtype() constructor interprets this as a request to give
    a default name.  Instead, we construct descriptor that can be passed to
    dtype().

    Parameters
    ----------
    dtype : dtype
        The dtype of the array that will be written to disk.

    Returns
    -------
    descr : object
        An object that can be passed to `numpy.dtype()` in order to
        replicate the input dtype.

    """
    if _has_metadata(dtype):
        warnings.warn("metadata on a dtype may be saved or ignored, but will "
                      "raise if saved when read. Use another form of storage.",
                      UserWarning, stacklevel=2)
    if dtype.names is not None:
        # This is a record array. The .descr is fine.  XXX: parts of the
        # record array with an empty name, like padding bytes, still get
        # fiddled with. This needs to be fixed in the C implementation of
        # dtype().
        return dtype.descr
    else:
        return dtype.str

def descr_to_dtype(descr):
    '''
    descr may be stored as dtype.descr, which is a list of
    (name, format, [shape]) tuples where format may be a str or a tuple.
    Offsets are not explicitly saved, rather empty fields with
    name, format == '', '|Vn' are added as padding.

    This function reverses the process, eliminating the empty padding fields.
    '''
    if isinstance(descr, str):
        # No padding removal needed
        return numpy.dtype(descr)
    elif isinstance(descr, tuple):
        # subtype, will always have a shape descr[1]
        dt = descr_to_dtype(descr[0])
        return numpy.dtype((dt, descr[1]))

    titles = []
    names = []
    formats = []
    offsets = []
    offset = 0
    for field in descr:
        if len(field) == 2:
            name, descr_str = field
            dt = descr_to_dtype(descr_str)
        else:
            name, descr_str, shape = field
            dt = numpy.dtype((descr_to_dtype(descr_str), shape))

        # Ignore padding bytes, which will be void bytes with '' as name
        # Once support for blank names is removed, only "if name == ''" needed)
        is_pad = (name == '' and dt.type is numpy.void and dt.names is None)
        if not is_pad:
            title, name = name if isinstance(name, tuple) else (None, name)
            titles.append(title)
            names.append(name)
            formats.append(dt)
            offsets.append(offset)
        offset += dt.itemsize

    return numpy.dtype({'names': names, 'formats': formats, 'titles': titles,
                        'offsets': offsets, 'itemsize': offset})

def header_data_from_array_1_0(array):
    """ Get the dictionary of header metadata from a numpy.ndarray.

    Parameters
    ----------
    array : numpy.ndarray

    Returns
    -------
    d : dict
        This has the appropriate entries for writing its string representation
        to the header of the file.
    """
    d = {'shape': array.shape}
    if array.flags.c_contiguous:
        d['fortran_order'] = False
    elif array.flags.f_contiguous:
        d['fortran_order'] = True
    else:
        # Totally non-contiguous data. We will have to make it C-contiguous